Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30574
    Prev
    Next
    INDEX
    Explanations

    Telling/saying

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Compared
    -0.08
    .the
    -0.08
     Whatever
    -0.08
    _AV
    -0.07
    Compared
    -0.07
     foc
    -0.07
     beautifully
    -0.07
     kleurr
    -0.07
     compared
    -0.07
    .Ab
    -0.07
    POSITIVE LOGITS
     hiatus
    0.09
     आदेश
    0.09
     delimiter
    0.09
     EOF
    0.09
     વિર
    0.09
    停止
    0.08
     cues
    0.08
    暂停
    0.08
     cue
    0.08
     akkoord
    0.08
    Activations Density 0.005%

    No Known Activations